Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    abuse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nivel
    -0.08
    phere
    -0.07
    YYYY
    -0.07
     deepen
    -0.06
     Penalty
    -0.06
    .spec
    -0.06
    EST
    -0.06
    (short
    -0.06
     Todos
    -0.06
    에게
    -0.06
    POSITIVE LOGITS
    veyor
    0.07
    Grab
    0.06
    抽
    0.06
     dominating
    0.06
    Subscribe
    0.06
    _Anim
    0.06
     bundle
    0.06
    检
    0.06
     Seks
    0.06
    JSONException
    0.06
    Act Density 0.001%

    No Known Activations